paper-with-me

홈 › Papers

Uncertainty Propagation in Deep Neural Network Using Active Subspace

2019-03-10 · Weiqi Ji, Zhuyin Ren, Chung K. Law

The inputs of deep neural network (DNN) from real-world data usually come with uncertainties. Yet, it is challenging to propagate the uncertainty in the input features to the DNN predictions at a low computational cost. This work employs a gradient-based subspace method and response surface technique to accelerate the uncertainty propagation in DNN. Specifically, the active subspace method is employed to identify the most important subspace in the input features using the gradient of the DNN output to the inputs. Then the response surface within that low-dimensional subspace can be efficiently built, and the uncertainty of the prediction can be acquired by evaluating the computationally cheap response surface instead of the DNN models. In addition, the subspace can help explain the adversarial examples. The approach is demonstrated in MNIST datasets with a convolutional neural network. Code is available at: https://github.com/jiweiqi/nnsubspace.

📄 PDF Abstract BibTeX arXiv:1903.03989

Code (1)

jiweiqi/nnsubspace 공식 구현

Similar Papers 제목 키워드 기반

Deep active subspaces - a scalable method for high-dimensional uncertainty propagation

2019-02-27 · Rohit Tripathy, Ilias Bilionis

A problem of considerable importance within the field of uncertainty quantification (UQ) is the development of efficient methods for the construction of accurate surrogate models. Such efforts are particularly important …

Dimensionality ReductionUncertainty QuantificationVocal Bursts Intensity Prediction

Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks

2023-09-06 · Sanket Jantre, Nathan M. Urban, Xiaoning Qian, Byung-Jun Yoon

Bayesian inference for neural networks, or Bayesian deep learning, has the potential to provide well-calibrated predictions with quantified uncertainty and robustness. However, the main hurdle for Bayesian deep learning …

Bayesian InferenceDeep LearningUncertainty QuantificationVariational Inference

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design

2024-04-30 · A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon

Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design model…

Bayesian InferenceDiversityDrug DesignUncertainty Quantification

Active Subspace of Neural Networks: Structural Analysis and Universal Attacks

2019-10-29 · Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev, Julia Gusak 외

Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability and deep neural networks using active subs…

Adversarial AttackUncertainty Quantification

Sequential Learning of Active Subspaces

2019-07-26 · Nathan Wycoff, Mickael Binois, Stefan M. Wild

In recent years, active subspace methods (ASMs) have become a popular means of performing subspace sensitivity analysis on black-box functions. Naively applied, however, ASMs require gradient evaluations of the target fu…

Gaussian ProcessesSensitivitysubspace methods